Related Experiment Video
Updated: Jun 14, 2026
15:48
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
22.9K
MRI-based radiomics to predict lipomatous soft tissue tumors malignancy: a pilot study
Benjamin Leporq1, Amine Bouhamama2, Frank Pilleul3,2
1Univ Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS UMR 5220, Villeurbanne, France. benjamin.leporq2@gmail.com.
Summary
This study developed a MRI radiomic method to predict malignancy in lipomatous soft tissue tumors. The model achieved high accuracy, showing promise for clinical use.
Area of Science:
- Radiology
- Oncology
- Medical Imaging
- Machine Learning
Background:
- Lipomatous soft tissue tumors require accurate differentiation between benign and malignant types.
- Current diagnostic methods can be limited, necessitating advanced imaging techniques.
Purpose of the Study:
- To develop and validate a magnetic resonance imaging (MRI)-based radiomic method for predicting malignancy in lipomatous soft tissue tumors.
- To assess the feasibility of using routinely acquired MRI data for this purpose.
Main Methods:
- Retrospective analysis of 81 patients with lipomatous soft tissue tumors and contrast-enhanced T1-weighted MRI.
- Extraction and selection of 35 reproducible and relevant radiomic features from 87 initially extracted features.
- Development of a linear support vector machine model to predict malignancy.
Main Results:
- A radiomic model was developed using 35 features, achieving high diagnostic performance.
- The model demonstrated an area under the receiver operating characteristic curve (AUROC) of 0.96.
- Excellent sensitivity (100%), specificity (90%), and overall accuracy (95.0%) were reported for malignancy prediction.
Conclusions:
- Radiomics, utilizing standard MRI acquisitions, can effectively predict malignancy in soft tissue lipomatous tumors.
- The developed method shows significant potential for clinical application in oncology.
- Further external validation is recommended to confirm these promising findings.
